Association,aiming to link bounding boxes of the same identity in a video sequence,is a central component in multi-object tracking(MOT).To train association modules,e.g.,parametric networks,real video data are usually...Association,aiming to link bounding boxes of the same identity in a video sequence,is a central component in multi-object tracking(MOT).To train association modules,e.g.,parametric networks,real video data are usually used.However,annotating person tracks in consecutive video frames is expensive,and such real data,due to its inflexibility,offer us limited opportunities to evaluate the system performance w.r.t.changing tracking scenarios.In this paper,we study whether 3D synthetic data can replace real-world videos for association training.Specifically,we introduce a large-scale synthetic data engine named MOTX,where the motion characteristics of cameras and objects are manually configured to be similar to those of real-world datasets.We show that,compared with real data,association knowledge obtained from synthetic data can achieve very similar performance on real-world test sets without domain adaption techniques.Our intriguing observation is credited to two factors.First and foremost,3D engines can well simulate motion factors such as camera movement,camera view,and object movement so that the simulated videos can provide association modules with effective motion features.Second,the experimental results show that the appearance domain gap hardly harms the learning of association knowledge.In addition,the strong customization ability of MOTX allows us to quantitatively assess the impact of motion factors on MOT,which brings new insights to the community.展开更多
The topics concerning intellectual property and the protection of traditional resources have been under international discussion coordinated by the World Intellectual Property Organization(WIPO)for more than 20 years....The topics concerning intellectual property and the protection of traditional resources have been under international discussion coordinated by the World Intellectual Property Organization(WIPO)for more than 20 years.The WIPO Treaty on Intellectual Property,Genetic Resources and Associated Traditional Knowledge was achieved based on the consensus of the origin-disclosure principle and defensive protection preventing the erroneous grant of patents,which leaves a gap with the"prior informed consent+sharing of benefit"mechanism championed by the Convention on Biological Diversity.For the traditional cultural expressions or folklore available in public,the copyright-like protection is controversial due to the obvious divergence between the view of exclusive rights protection and that of free public domain.From the trend of negotiations on reaching an international instrument,a shift from the expectation of"license&royalty"to"attribution&moral rights"as a bottom line might be more realistic for the protection of such folklore already in the public domain,and it is desirable to fully utilize the existing intellectual property system to safeguard the transmission and utilization of folklore by local communities.Adjustments to domestic law should follow the same rationale.展开更多
基金supported by the ARC Discovery Early Career Researcher Award,China(No.DE200101283)the ARC Discovery Project,China(No.DP210102801).
文摘Association,aiming to link bounding boxes of the same identity in a video sequence,is a central component in multi-object tracking(MOT).To train association modules,e.g.,parametric networks,real video data are usually used.However,annotating person tracks in consecutive video frames is expensive,and such real data,due to its inflexibility,offer us limited opportunities to evaluate the system performance w.r.t.changing tracking scenarios.In this paper,we study whether 3D synthetic data can replace real-world videos for association training.Specifically,we introduce a large-scale synthetic data engine named MOTX,where the motion characteristics of cameras and objects are manually configured to be similar to those of real-world datasets.We show that,compared with real data,association knowledge obtained from synthetic data can achieve very similar performance on real-world test sets without domain adaption techniques.Our intriguing observation is credited to two factors.First and foremost,3D engines can well simulate motion factors such as camera movement,camera view,and object movement so that the simulated videos can provide association modules with effective motion features.Second,the experimental results show that the appearance domain gap hardly harms the learning of association knowledge.In addition,the strong customization ability of MOTX allows us to quantitatively assess the impact of motion factors on MOT,which brings new insights to the community.
文摘The topics concerning intellectual property and the protection of traditional resources have been under international discussion coordinated by the World Intellectual Property Organization(WIPO)for more than 20 years.The WIPO Treaty on Intellectual Property,Genetic Resources and Associated Traditional Knowledge was achieved based on the consensus of the origin-disclosure principle and defensive protection preventing the erroneous grant of patents,which leaves a gap with the"prior informed consent+sharing of benefit"mechanism championed by the Convention on Biological Diversity.For the traditional cultural expressions or folklore available in public,the copyright-like protection is controversial due to the obvious divergence between the view of exclusive rights protection and that of free public domain.From the trend of negotiations on reaching an international instrument,a shift from the expectation of"license&royalty"to"attribution&moral rights"as a bottom line might be more realistic for the protection of such folklore already in the public domain,and it is desirable to fully utilize the existing intellectual property system to safeguard the transmission and utilization of folklore by local communities.Adjustments to domestic law should follow the same rationale.
